MuleRouter Documentation - AI API Gateway & Routing Platform

Create chat completion

curl --request POST \
  --url https://api.mulerouter.ai/vendors/openai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen3-max",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello! How are you?"
    }
  ]
}
'

import requests

url = "https://api.mulerouter.ai/vendors/openai/v1/chat/completions"

payload = {
    "model": "qwen3-max",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Hello! How are you?"
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'qwen3-max',
    messages: [
      {role: 'system', content: 'You are a helpful assistant.'},
      {role: 'user', content: 'Hello! How are you?'}
    ]
  })
};

fetch('https://api.mulerouter.ai/vendors/openai/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.mulerouter.ai/vendors/openai/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'qwen3-max',
    'messages' => [
        [
                'role' => 'system',
                'content' => 'You are a helpful assistant.'
        ],
        [
                'role' => 'user',
                'content' => 'Hello! How are you?'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.mulerouter.ai/vendors/openai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"qwen3-max\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello! How are you?\"\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.mulerouter.ai/vendors/openai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"qwen3-max\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello! How are you?\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.mulerouter.ai/vendors/openai/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"qwen3-max\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello! How are you?\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "id": "chatcmpl-fJ5wOo5nqnWz2Z9jkF4NK",
  "object": "chat.completion",
  "created": 1715392980,
  "model": "qwen3-max",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How are you?",
        "refusal": null,
        "annotations": []
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 10,
    "total_tokens": 20,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "cached_tokens": 0,
      "audio_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    }
  }
}

POST

vendors

openai

chat

completions

Create chat completion

curl --request POST \
  --url https://api.mulerouter.ai/vendors/openai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "qwen3-max",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello! How are you?"
    }
  ]
}
'

import requests

url = "https://api.mulerouter.ai/vendors/openai/v1/chat/completions"

payload = {
    "model": "qwen3-max",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Hello! How are you?"
        }
    ]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'qwen3-max',
    messages: [
      {role: 'system', content: 'You are a helpful assistant.'},
      {role: 'user', content: 'Hello! How are you?'}
    ]
  })
};

fetch('https://api.mulerouter.ai/vendors/openai/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.mulerouter.ai/vendors/openai/v1/chat/completions",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'qwen3-max',
    'messages' => [
        [
                'role' => 'system',
                'content' => 'You are a helpful assistant.'
        ],
        [
                'role' => 'user',
                'content' => 'Hello! How are you?'
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.mulerouter.ai/vendors/openai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"qwen3-max\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello! How are you?\"\n    }\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.mulerouter.ai/vendors/openai/v1/chat/completions")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"qwen3-max\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello! How are you?\"\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.mulerouter.ai/vendors/openai/v1/chat/completions")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"qwen3-max\",\n  \"messages\": [\n    {\n      \"role\": \"system\",\n      \"content\": \"You are a helpful assistant.\"\n    },\n    {\n      \"role\": \"user\",\n      \"content\": \"Hello! How are you?\"\n    }\n  ]\n}"

response = http.request(request)
puts response.read_body

{
  "id": "chatcmpl-fJ5wOo5nqnWz2Z9jkF4NK",
  "object": "chat.completion",
  "created": 1715392980,
  "model": "qwen3-max",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How are you?",
        "refusal": null,
        "annotations": []
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 10,
    "total_tokens": 20,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "cached_tokens": 0,
      "audio_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    }
  }
}

This API is compatible with OpenAI’s format.For more details, please refer to OpenAI’s official documentation.Not all models support all parameters.

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

messages

required

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

Minimum array length: 1

Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, developer messages replace the previous system messages.

Show child attributes

model

string

required

Model ID used to generate the response, like qwen3-max or gpt-5. Mulerouter offers a wide range of models with different capabilities, performance characteristics, and price points. to browse and compare available models.

metadata

object | null

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Show child attributes

top_logprobs

integer

An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

Required range: 0 <= x <= 20

temperature

number | null

default:1

What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.

Required range: 0 <= x <= 2

Example:

1

top_p

number | null

default:1

An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

We generally recommend altering this or temperature but not both.

Required range: 0 <= x <= 1

Example:

1

user

string

deprecated

This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. information.

Example:

"user-1234"

service_tier

enum<string> | null

default:auto

Specifies the processing type used for serving the request.

If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
When not set, the default behavior is 'auto'.

When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.

Available options:

auto,

default,

flex,

scale,

priority

modalities

enum<string>[] | null

Output types that you would like the model to generate. Most models are capable of generating text, which is the default:

["text"]

The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:

["text", "audio"]

Available options:

text,

audio

verbosity

enum<string> | null

default:medium

Constrains the verbosity of the model's response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.

Available options:

low,

medium,

high

reasoning_effort

enum<string> | null

default:medium

Constrains effort on reasoning for reasoning models. Currently supported values are minimal, low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

Available options:

minimal,

low,

medium,

high

max_completion_tokens

integer | null

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.

frequency_penalty

number | null

default:0

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.

Required range: -2 <= x <= 2

presence_penalty

number | null

default:0

Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

Required range: -2 <= x <= 2

web_search_options

Web search · object

This tool searches the web for relevant results to use in a response.

Show child attributes

response_format

Text · object

An object specifying the format that the model must output.

Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema.

Setting to { "type": "json_object" } enables the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.

Text
JSON schema
JSON object

Show child attributes

audio

object | null

Parameters for audio output. Required when audio output is requested with modalities: ["audio"].

Show child attributes

store

boolean | null

default:false

Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

Supports text and image inputs. Note: image inputs over 8MB will be dropped.

stream

boolean | null

default:false

If set to true, the model response data will be streamed to the client as it is generated using server-sent events.

stop

default:<|endoftext|>

Not supported with latest reasoning models o3 and o4-mini.

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

Example:

"\n"

logit_bias

object | null

Modify the likelihood of specified tokens appearing in the completion.

Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token.

Show child attributes

logprobs

boolean | null

default:false

Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message.

max_tokens

integer | null

deprecated

The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API.

This value is now deprecated in favor of max_completion_tokens, and is not compatible with o-series models.

integer | null

default:1

How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs.

Required range: 1 <= x <= 128

Example:

1

prediction

Static Content · object | null

Configuration for a Predicted Output which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content.

Show child attributes

seed

integer | null

deprecated

This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed, and you should refer to the system_fingerprint response parameter to monitor changes in the backend.

Required range: -9223372036854776000 <= x <= 9223372036854776000

stream_options

object | null

Options for streaming response. Only set this when you set stream: true.

Show child attributes

tools

(Function tool · object | Custom tool · object)[]

A list of tools the model may call. You can provide either custom tools or function tools.

A function tool that can be used to generate a response.

Function tool
Custom tool

Show child attributes

tool_choice

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

none is the default when no tools are present. auto is the default if tools are present.

Available options:

none,

auto,

required

parallel_tool_calls

boolean

default:true

Whether to enable parallel function calling during tool use.

function_call

deprecated

Deprecated in favor of tool_choice.

Controls which (if any) function is called by the model.

none means the model will not call a function and instead generates a message.

auto means the model can pick between generating a message or calling a function.

Specifying a particular function via {"name": "my_function"} forces the model to call that function.

none is the default when no functions are present. auto is the default if functions are present.

Available options:

none,

auto

functions

object[]

deprecated

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

Required array length: 1 - 128 elements

Show child attributes

Response

Represents a chat completion response returned by model, based on the provided input.

string

required

A unique identifier for the chat completion.

choices

object[]

required

A list of chat completion choices. Can be more than one if n is greater than 1.

Show child attributes

created

integer

required

The Unix timestamp (in seconds) of when the chat completion was created.

model

string

required

The model used for the chat completion.

object

enum<string>

required

The object type, which is always chat.completion.

Available options:

chat.completion

service_tier

enum<string> | null

default:auto

Specifies the processing type used for serving the request.

If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.
If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.
If set to 'flex' or 'priority', then the request will be processed with the corresponding service tier.
When not set, the default behavior is 'auto'.

Available options:

auto,

default,

flex,

scale,

priority

system_fingerprint

string

deprecated

This fingerprint represents the backend configuration that the model runs with.

Can be used in conjunction with the seed request parameter to understand when backend changes have been made that might impact determinism.

usage

object

Usage statistics for the completion request.

Show child attributes

Reference

Account

LLM

Image Generation

Video Generation

Speech Generation

Music Generation

Create Chat Completion

Authorizations

Body

Response